Underspecified feature models for pronunciation variation in ASR
Eric Fosler-Lussier
Acoustic and linguistic characterization of spontaneous speech
Masanobu Nakamura, Sadaoki Furui, Koji Iwano
Analysis of model adaptation on non-native speech for multiple accent speech recognition
Denis Jouvet, Katarina Bartkova
Improved context integration for robust speech recognition in conversational systems
Georg Stemmer
Whither linguistic interpretation of acoustic pronunciation variation
Annika Hämäläinen, Yan Han, Lou Boves, Louis ten Bosch
Speech variation and the use of distance metrics on the articulatory feature space
Louis ten Bosch
How to handle pronunciation variation in ASR: by storing episodes in memory?
Helmer Strik
Intra-speaker variation and units in human speech perception and ASR
Richard Wright
Improvement of feature vectors in clean and telephone speech recognition using bidirectional neural network
Mansoor Vali, Seyyed Ali Seyyed Salehi, Kazem Karimi
Theorem of the invariant structure and its derivation of speech gestalt
Nobuaki Minematsu, Tazuko Nishimura, Katsuhiro Nishinari, Kyoko Sakuraba
On the distribution of information and intrinsic variability for classification of coarticulated vowels
Sorin Dusan
A flexible recogniser architecture in a reading tutor for children
Jacques Duchateau, Mari Wigham, Kris Demuynck, Hugo van Hamme
Analysis of the modeling of pitch and voicing parameters for speaker-independent speech recognition systems
Gwenael Cloarec, Denis Jouvet, Jean Monné
Utterance-based selective training for cost-effective task-adaptation of acoustic models
Tobias Cincarek, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano
Capturing fine-phonetic variation in speech through automatic classification of articulatory features
Odette Scharenborg, Vincent Wan, Roger K. Moore
Comparative study of different features on OLLO logatome recognition task
Vivek Tyagi, Mohammed Benzheghiba, Milos Cernak, Christian Wellekens
A general method for combining acoustic features in an automatic speech recognition system
Driss Matrouf, Loic Barrault, Renato De Mori
A human-machine comparison in speech recognition based on a logatome corpus
Bernd Meyer, Thorsten Wesker, Thomas Brand, Alfred Mertins, Birger Kollmeier
Half a word is enough for listeners, but problematic for ASR
Helmer Strik, A. Elffers, D. Bavcar, Catia Cucchiarini
Multiple acoustic and variability estimation models for ASR
Stéphane Dupont, Christophe Ris
Acoustic modeling of accented English speech for large-vocabulary speech recognition
Konstantin Markov, Satoshi Nakamura
Cross entropy information metric for quantification and cluster analysis of accents
Seyed Alireza Ghorshi, Saeed Vaseghi, Qin Yan
A study of auditory-filterbank based preprocessing for the generation of warping-invariant features
Jan Rademacher, Alfred Mertins
The influence of word detection variability on IR performance in automatic audio indexing of course lectures
Renato Rispoli, Richard C. Rose, Jon Arrowood
Towards speaker and enviromental robustness in ASR: the HIWIRE project
A. Potamianos, G. Bouselmi, D. Dimitriadis, Dominique Fohr, Roberto Gemello, I. Illina, Franco Mana, P. Maragos, M. Matassoni, V. Pitsikalis, J. Ramirez, E. Sanchez-Soto, J. Segura, P. Svaizer
Adapting hybrid ANN/HMM to speech variations
Stefano Scanzio, Dario Albesano, Roberto Gemello, Pietro Laface, Franco Mana